基于加权优先级和分类匹配的图像修复方法

doi:10.11959/j.issn.1000-0801.2017103

电信科学 ›› 2017, Vol. 33 ›› Issue (4): 94-100.doi: 10.11959/j.issn.1000-0801.2017103

基于加权优先级和分类匹配的图像修复方法

曹燕,金炜,符冉迪

宁波大学信息科学与工程学院，浙江宁波 315211

修回日期:2017-04-04 出版日期:2017-04-01 发布日期:2017-04-26
作者简介:曹燕（1993-），女，宁波大学信息科学与工程学院硕士生，主要研究方向为数字图像处理、模式识别。|金炜（1969-），男，宁波大学信息科学与工程学院副教授、硕士生导师，主要从事压缩感知、模式识别和数字图像处理等方面的研究工作。|符冉迪（1971-），男，宁波大学信息科学与工程学院副教授、硕士生导师，主要从事数字图像处理、模式识别等方面的研究工作。
基金资助:
浙江省自然科学基金资助项目(LY16F010001);国家自然科学基金资助项目(61471212);宁波市自然科学基金资助项目(2016A610091)

An image inpainting method based on weighted priority and classification matching

Yan CAO,Wei JIN,Randi FU

Faculty of Electrical Engineering and Computer Science,Ningbo University,Ningbo 315211,China

Revised:2017-04-04 Online:2017-04-01 Published:2017-04-26
Supported by:
The Natural Science Foundation of Zhejiang Province of China(LY16F010001);The National Natural Science Foundation of China(61471212);The Natural Science Foundation of Ningbo of China(2016A610091)

摘要/Abstract

摘要：

待修复像素优先级的计算及最佳匹配块的确定是基于纹理合成图像修复方法的两个基本环节，传统方法不仅难于确定优先级计算中的置信度，而且难于搜索到最佳匹配块。提出了一种基于加权优先级和分类匹配的图像修复方法，该方法在优先级模型中，引入指数函数和正规化函数分别优化置信度和数据项，使得计算的优先级更加客观，从而使修复顺序更加合理。基于此，将结构信息作为搜索匹配块的一个度量因子，采用分类筛选方式，选取最佳匹配块。实验结果表明，所提方法在获得良好修复效果的前提下缩短了修复时间。

关键词: 纹理合成, 图像修复, 优先级, 匹配方式

Abstract:

The calculation of the priority of the pixel to be repaired and the determination of the best matching block are based on two basic steps of the texture synthesis image inpainting method.The traditional method is not suitable because it is difficult to determine the confidence in the priority calculation,and it is difficult to search for the best matching block.An image inpainting method based on weighted priority and classification matching was proposed.In the priority model,the exponential function and the normalization function were introduced to optimize the confidence and data items separately,the further benefit of which was a more objective priority of calculation and a more reasonable repair order.Based on the proposed functions,the structure information was used as a measure factor of the search matching block,and the best matching block was selected by the classification and screening method.Experimental results show that the proposed method can shorten the repair time under the condition of obtaining good repair effect.

Key words: texture synthesis, image inpainting, priority, matching criteria

中图分类号:

TP391

曹燕,金炜,符冉迪. 基于加权优先级和分类匹配的图像修复方法[J]. 电信科学, 2017, 33(4): 94-100.

Yan CAO,Wei JIN,Randi FU. An image inpainting method based on weighted priority and classification matching[J]. Telecommunications Science, 2017, 33(4): 94-100.

图/表 6

图1

图2

图3

表1

图4

表2

参考文献 11

[1]	BERTALMIO M , SAPIRO G , CASELLES V , et al. Image inpainting[C]// The 27th Annual Conference on Computer Graphics and Interactive Techniques, July 23-28,2002,Las Vegas,NV,USA. New Orleans,USA.[S.l.:s.n.], 2002:417-424.
[2]	CHAN T F , SHEN J . Non-texture inpainting by curvature-driven diffusions(CDD)[J]. Journal of Visual Communication and Image Representation, 2001,12(4):436-449.
[3]	XU Z B , SUN J . Image inpainting by patch propagation using patch sparsity[J]. IEEE Transactions on Image Processing, 2010,19(5):1153-1165.
[4]	CRIMINISI A , PEREA P , TOYAMA K . Region filling and object removal by exemplar-based image inpainting[J]. IEEE Transactions on Image Processing, 2004,13(9):1200-1212.
[5]	李旭峰，王静，刘红敏，等. 特征优先块匹配图像修复算法[J]. 计算机辅助设计与图形学学报， 2016,28(7):1131-1137.
	LI X F , WANG J , LIU H M , et al. Image inpainting using feature precedence and patch matching[J]. Journal of Computer-Aided Design and Computer Graphics, 2016,28(7):1131-1137.
[6]	WANG J , LU K , PAN D , et al. Robust object removal with an exemplar based image inpainting approach[J]. Neurocomputing, 2014,123(10):150-155.
[7]	CHEN Z , DAI C , JIANG L , et al. Structure-aware image inpainting using patch scale optimization[J]. Journal of Visual Communication ＆ Image Representation, 2016(40):312-323.
[8]	李志丹，和红杰，尹忠科，等. 基于Curvelet方向特征的样本块图像修复算法[J]. 电子学报， 2016,44(1):150-154.
	LI Z D , HE H J , YIN Z K , et al. Exemplar based image inpainting algorithm using direction features of Curvelet transform[J]. Acta Electronica Sinica, 2016,44(1):150-154.
[9]	CHENG W H , HSIEH C W , LIN S K , et al. Robust algorithm for exemplar-based image inpainting[C]// The International Conference on Computer Graphics,Imaging and Vision(CGIV), July 26-29,2005,Las Vegas,NV,USA. Beijing,China: IEEE Press, 2005:64-69.
[10]	WANG Z , BOVIK A C , SHEIKH H R , et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004,13(4):600-612.
[11]	SHIH T K , CHANG R C , LU L C , et al. Adaptive digital image inpainting[C]// International Conference on Advanced Information Networking and Applications, March 29-31,2004,Los Alamitos,USA. New Jersey: IEEE Press, 2004:71-76.

算法	图2	图3
Criminisi算法	34.139 7	27.155 5
参考文献[6]算法	36.445 7	29.003 2
本文方法	38.248 8	34.135 2

图像	图像大小	破损像素/dpi	Criminisi算法/s	参考文献[6]算法/s	本文方法/s
图2	512 dpi × 512 dpi	2 381	12 470.9	1 624.5	470.7
图3	292 dpi × 304 dpi	5 007	2 598.9	1 222.6	137.7
图4	308 dpi × 206 dpi	7 954	25 662.8	10 126.6	2 760.2

基于加权优先级和分类匹配的图像修复方法

An image inpainting method based on weighted priority and classification matching

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 11

相关文章 4

Metrics

推荐阅读 0

[1]	谢石木林, 白杰, 张翔, 汤泽毅, 粘为帆, 刘旭杰. 基于5G+MEC的电网边缘计算平台任务安全性调度方法[J]. 电信科学, 2022, 38(12): 78-85.
[2]	周晓勇,申滨,徐浪,黄晓舸. 基于SRS优先级划分及时移传输机制的SL空口同步方案[J]. 电信科学, 2018, 34(12): 1-9.
[3]	王明伟,李琴,王奇,林建中. 基于分层多播的视频传输拥塞控制算法研究[J]. 电信科学, 2010, 26(5): 78-82.
[4]	周永刚,钱宗珏,寿国础,胡怡红. EPON系统中基于业务等级的动态带宽算法研究[J]. 电信科学, 2006, 22(3): 68-70.